Update new layer diagram (#371)

Signed-off-by: Dan Sun <[email protected]>
kserve · Jun 9, 2024 · fb8dbde · fb8dbde
1 parent f41252e
commit fb8dbde
Show file tree

Hide file tree

Showing 5 changed files with 12 additions and 14 deletions.
diff --git a/docs/modelserving/v1beta1/llm/huggingface/README.md b/docs/modelserving/v1beta1/llm/huggingface/README.md
@@ -62,7 +62,7 @@ curl -H "content-type:application/json" -H "Host: ${SERVICE_HOSTNAME}" -v http:/
 ```
 !!! success "Expected Output"
 
-  ```{ .bash .no-copy }
+  ```{ .json .no-copy }
     {"id":"cmpl-7c654258ab4d4f18b31f47b553439d96","choices":[{"finish_reason":"length","index":0,"logprobs":null,"text":"<generated_text>"}],"created":1715353182,"model":"llama3","system_fingerprint":null,"object":"text_completion","usage":{"completion_tokens":26,"prompt_tokens":4,"total_tokens":30}}
   ```
 
@@ -74,7 +74,7 @@ curl -H "content-type:application/json" -H "Host: ${SERVICE_HOSTNAME}" -v http:/
 ```
 !!! success "Expected Output"
 
-  ```{ .bash .no-copy }
+  ```{ .json .no-copy }
     {"id":"cmpl-87ee252062934e2f8f918dce011e8484","choices":[{"finish_reason":"length","index":0,"message":{"content":"<generated_response>","tool_calls":null,"role":"assistant","function_call":null},"logprobs":null}],"created":1715353461,"model":"llama3","system_fingerprint":null,"object":"chat.completion","usage":{"completion_tokens":30,"prompt_tokens":3,"total_tokens":33}}
   ```
 

diff --git a/docs/modelserving/v1beta1/llm/huggingface/python_runtime.yaml b/docs/modelserving/v1beta1/llm/huggingface/python_runtime.yaml
@@ -1,17 +1,17 @@
 apiVersion: serving.kserve.io/v1beta1
 kind: InferenceService
 metadata:
-  name: huggingface-llama2
+  name: huggingface-llama3
 spec:
   predictor:
     model:
       modelFormat:
         name: huggingface
       args:
-      - --model_name=llama2
-      - --model_id=meta-llama/Llama-2-7b-chat-hf
+      - --model_name=llama3
+      - --model_id=meta-llama/meta-llama-3-8b-instruct
       - --tensor_input_names=input_ids
-      - --disable_vllm
+      - --backend=huggingface
       resources:
         limits:
           cpu: "6"

diff --git a/docs/modelserving/v1beta1/llm/huggingface/vllm_runtime.yaml b/docs/modelserving/v1beta1/llm/huggingface/vllm_runtime.yaml
@@ -1,15 +1,15 @@
 apiVersion: serving.kserve.io/v1beta1
 kind: InferenceService
 metadata:
-  name: huggingface-llama2
+  name: huggingface-llama3
 spec:
   predictor:
     model:
       modelFormat:
         name: huggingface
       args:
-      - --model_name=llama2
-      - --model_id=meta-llama/Llama-2-7b-chat-hf
+      - --model_name=llama3
+      - --model_id=meta-llama/meta-llama-3-8b-instruct
       resources:
         limits:
           cpu: "6"

diff --git a/mkdocs.yml b/mkdocs.yml
@@ -42,10 +42,8 @@ nav:
                   - Hugging Face: modelserving/v1beta1/triton/huggingface/README.md
                 - AMD: modelserving/v1beta1/amd/README.md
               - LLM Runtime:
-                - TorchServe LLM:
-                  - Bloom7b1: modelserving/v1beta1/llm/torchserve/accelerate/README.md
-                - Hugging Face LLM:
-                  - Llama2: modelserving/v1beta1/llm/huggingface/README.md
+                - Hugging Face LLM: modelserving/v1beta1/llm/huggingface/README.md
+                - TorchServe LLM: modelserving/v1beta1/llm/torchserve/accelerate/README.md
               - How to write a custom predictor: modelserving/v1beta1/custom/custom_model/README.md
           - Multi Model Serving:
                 - Overview:

diff --git a/overrides/home.html b/overrides/home.html
@@ -22,7 +22,7 @@ <h2>Highly scalable and standards based
         </p>
       </div>
       <div>
-        <img src="./images/kserve_layer.png" />
+        <img src="./images/kserve_new.png" />
       </div>
     </div>
   </section>
-Original file line number
+Diff line change
@@ Expand Up / @@ -22,7 +22,7 @@ <h2>Highly scalable and standards based @@
             </p>
           </div>
           <div>
-            <img src="./images/kserve_layer.png" />
+            <img src="./images/kserve_new.png" />
           </div>
         </div>
       </section>
@@ Expand Down @@